Claude Haiku 5.5 is $0.1 cheaper per 1M input tokens (50% lower; 2x difference).
API cost decision in 10 seconds
NewClaude Haiku 5.5 vs Mercury 2.5 Preview
Pick Claude Haiku 5.5 when budget and context both matter.
Page updated:
Data confirmed:
Prices normalized to USD per 1M tokens
Sample workload: 1M input + 500K output
Budget verdict
Pick Claude Haiku 5.5 when budget and context both matter.
On the standard 1M input plus 500K output workload, Claude Haiku 5.5 is estimated at $0.35 vs $0.57 for Mercury 2.5 Preview, saving $0.22 (39.1% lower).
Cost-first pickClaude Haiku 5.5
Context-first pickClaude Haiku 5.5
Sample savings$0.2239.1%
10x traffic gap$2.25
Claude Haiku 5.5 is cheaper on the standard workload and also has the larger context window. At 10x that traffic, the same price gap is about $2.25. Use the calculator below to replace the sample workload with your own token volume.
Cost sensitivity
Workload Sensitivity
Claude Haiku 5.5 stays cheaper across input-heavy, balanced, and output-heavy sample workloads.
| Workload shape | Token mix | Better pick | Claude Haiku 5.5 | Mercury 2.5 Preview |
|---|---|---|---|---|
| Input-heavy / RAG | 5M input + 500K output | Claude Haiku 5.5 | $0.75 | $1.38 |
| Balanced workload | 1M input + 1M output | Claude Haiku 5.5 | $0.6 | $0.95 |
| Output-heavy chatbot | 1M input + 5M output | Claude Haiku 5.5 | $2.6 | $3.95 |
Claude Haiku 5.5 is $0.25 cheaper per 1M output tokens (33.3% lower; 1.5x difference).
Claude Haiku 5.5 has 740K more context (3.85x larger).
Claude Haiku 5.5 is $0.22 cheaper on the standard workload (39.1% lower).
Estimate your workload cost
Your Workload Cost
This estimate uses normalized public API pricing per 1M tokens. It is a planning aid, not a billing quote. Verify provider pricing, limits, and terms before production use.
Quick Decision
Claude Haiku 5.5 has the lower input price; Claude Haiku 5.5 has the lower output price; Claude Haiku 5.5 offers the larger context window. For the 1M input plus 500K output sample, Claude Haiku 5.5 is cheaper for the standard workload.
For a 1M input token plus 500K output token workload, the estimated API cost is $0.35 for Claude Haiku 5.5 and $0.57 for Mercury 2.5 Preview.
Choose Claude Haiku 5.5 when you care most about lower input-token price, lower output-token price, and larger context window.
Choose Mercury 2.5 Preview when its provider, model quality, latency, or availability is more important than the numeric price/context winner.
- On the standard 1M input plus 500K output workload, Claude Haiku 5.5 is estimated at $0.35 vs $0.57 for Mercury 2.5 Preview, saving $0.22 (39.1% lower).
- Claude Haiku 5.5 is $0.22 cheaper on the standard workload (39.1% lower).
- Claude Haiku 5.5 is $0.1 cheaper per 1M input tokens (50% lower; 2x difference).
- Claude Haiku 5.5 is $0.25 cheaper per 1M output tokens (33.3% lower; 1.5x difference).
- Claude Haiku 5.5 has 740K more context (3.85x larger).
| Feature | NewClaude Haiku 5.5 (Anthropic) | Mercury 2.5 Preview (Inception) |
|---|---|---|
| Input Price prompt tokens per 1M | $0.1 | $0.2 |
| Completion Price per 1M tokens | $0.5 | $0.75 |
| Sample Workload Cost 1M input + 500K output | $0.35 | $0.57 |
| Context Window | 1M | 260K |
| Release Date |
Use-Case Decision Matrix
| Use case | Better pick | Why |
|---|---|---|
| Budget-constrained production | Claude Haiku 5.5 | On the standard 1M input plus 500K output workload, Claude Haiku 5.5 is estimated at $0.35 vs $0.57 for Mercury 2.5 Preview, saving $0.22 (39.1% lower). |
| High-volume input processing | Claude Haiku 5.5 | Lower prompt-token price matters most when prompts, retrieved passages, or documents dominate the bill. |
| Long responses and chatbots | Claude Haiku 5.5 | Lower output-token price matters most when assistants generate many completion tokens. |
| RAG or long-document work | Claude Haiku 5.5 | A larger context window leaves more room for retrieved passages, conversation history, or source files. |
Related Alternatives
- Claude Haiku 5.5 (batch) can replace Claude Haiku 5.5 when lower sample workload cost matters most: $0.17.
- Mercury 2.5 can replace Mercury 2.5 Preview when lower sample workload cost matters most: $0.11.
- Llama 4 Scout offers 1.31M context with $0.47 sample workload cost.
- MiMo-V2.6-Flash offers 1.05M context with $0.28 sample workload cost.
- GPT-6 Luna offers 1.05M context with $0.35 sample workload cost.
- GPT-6 Luna Pro offers 1.05M context with $0.35 sample workload cost.
- DeepSeek V4.1 Flash · DeepSeek · #1
- Step 5 Preview · StepFun · #2
- GLM 5.3 Flash · Z.ai · #3
- MiMo-V2.6-Flash · Xiaomi · #4
Cheaper alternatives
Review low-cost models sorted by a standard 1M input plus 500K output workload.
Open cheapest modelsLarger context alternatives
Find models with larger context windows for RAG, long documents, and codebase review.
Open largest context modelsProvider catalogs
Compare models within provider hubs before choosing a final API vendor.
Open provider hubsAnthropic catalog
Review all tracked Anthropic models before deciding whether this matchup is the right shortlist.
Open Anthropic modelsInception catalog
Check other Inception models with comparable pricing, context, or release timing.
Open Inception modelsClaude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and...
Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, Mercury 2.5 produces and refines multiple tokens in parallel, achieving...